Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -25,11 +25,15 @@
import org.apache.beam.sdk.io.Source;
import org.apache.beam.sdk.io.UnboundedSource;
import org.apache.beam.sdk.options.PipelineOptions;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/** Shared Beam source sizing and splitting helpers. */
final class FlinkSourceSplitUtils {
static final long MEBIBYTE = 1024L * 1024L;

private static final Logger LOG = LoggerFactory.getLogger(FlinkSourceSplitUtils.class);

private FlinkSourceSplitUtils() {}

static <T> long estimateBoundedSourceSize(
Expand All @@ -45,13 +49,25 @@ static <T> ArrayList<FlinkSourceSplit<T>> splitBoundedSource(
throws Exception {
long desiredSizeBytes =
getDesiredSizeBytes(boundedSource, pipelineOptions, numSplits, estimatedSizeBytes);
return toFlinkSplits(boundedSource.split(desiredSizeBytes, pipelineOptions));
List<? extends BoundedSource<T>> splits =
boundedSource.split(desiredSizeBytes, pipelineOptions);
LOG.info(
"Split bounded source {} in {} splits (estimated size {} bytes, "
+ "desired split size {} bytes)",
boundedSource,
splits.size(),
estimatedSizeBytes,
desiredSizeBytes);
return toFlinkSplits(splits);
}

static <T> ArrayList<FlinkSourceSplit<T>> splitUnboundedSource(
UnboundedSource<T, ?> unboundedSource, PipelineOptions pipelineOptions, int numSplits)
throws Exception {
return toFlinkSplits(unboundedSource.split(numSplits, pipelineOptions));
List<? extends UnboundedSource<T, ?>> splits =
unboundedSource.split(numSplits, pipelineOptions);
LOG.info("Split source {} to {} splits", unboundedSource, splits);
return toFlinkSplits(splits);
}

static long getDesiredSizeBytes(
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -131,11 +131,6 @@ private FlinkSourceEnumeratorState<T> selectAndSplit() throws Exception {
ArrayList<FlinkSourceSplit<T>> splits =
FlinkSourceSplitUtils.splitBoundedSource(
boundedSource, pipelineOptions, numSplits, estimatedSizeBytes);
LOG.info(
"Split bounded source {} into {} splits using {} assignment",
boundedSource,
splits.size(),
selectedMode);
return new FlinkSourceEnumeratorState<>(selectedMode, splits);
}

Expand Down
Loading